Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5840 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2120. Min Range: -4.2120
Max Act: 4.2120. Min Act: -0.1700
Data Index: 2359092 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2120. Min Range: -4.2120
Max Act: 3.9619. Min Act: -0.1700
Data Index: 669766 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2120. Min Range: -4.2120
Max Act: 3.9307. Min Act: -0.1700
Data Index: 8795011 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2120. Min Range: -4.2120
Max Act: 3.8994. Min Act: -0.1700
Data Index: 3381438 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2120. Min Range: -4.2120
Max Act: 3.8681. Min Act: -0.1700
Data Index: 1864001 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2120. Min Range: -4.2120
Max Act: 3.8994. Min Act: -0.1700
Data Index: 2692259 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2120. Min Range: -4.2120
Max Act: 3.8681. Min Act: -0.1700
Data Index: 40366 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2120. Min Range: -4.2120
Max Act: 3.8056. Min Act: -0.1700
Data Index: 3078275 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2120. Min Range: -4.2120
Max Act: 3.8369. Min Act: -0.1700
Data Index: 8744222 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2120. Min Range: -4.2120
Max Act: 3.8681. Min Act: -0.1700
Data Index: 52448 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2120. Min Range: -4.2120
Max Act: 3.8369. Min Act: -0.1700
Data Index: 2285719 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2120. Min Range: -4.2120
Max Act: 3.8369. Min Act: -0.1700
Data Index: 4738067 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2120. Min Range: -4.2120
Max Act: 3.8369. Min Act: -0.1700
Data Index: 2623591 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2120. Min Range: -4.2120
Max Act: 3.7743. Min Act: -0.1700
Data Index: 7973261 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2120. Min Range: -4.2120
Max Act: 3.8056. Min Act: -0.1700
Data Index: 7963611 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2120. Min Range: -4.2120
Max Act: 3.8369. Min Act: -0.1700
Data Index: 7683346 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2120. Min Range: -4.2120
Max Act: 3.8056. Min Act: -0.1700
Data Index: 5287401 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2120. Min Range: -4.2120
Max Act: 3.8056. Min Act: -0.1700
Data Index: 5283005 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2120. Min Range: -4.2120
Max Act: 3.8056. Min Act: -0.1700
Data Index: 3585136 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2120. Min Range: -4.2120
Max Act: 3.8056. Min Act: -0.1700
Data Index: 1562120 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19